Benchmarks of G9v3 39A5B12
BenchmarkByScoreRank
Overall1
Knowledge3
Science3
Agents2
Documents1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
self-host onlyprice
—output speed?
131Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam17.5#133
AA Omniscience Index3.8#56
CritPt (physics)0.3#149
AA Intelligence Index 4.3.2≈21.8#106
AA Omniscience · Accuracy14.9#237
AA-LCR (long context) 1.165.3#140
GPQA Diamond80.5#115
Coding
SciCode36.8#109
Terminal-Bench 2.132.6#94
Agents & Tool Use
GDPval-AA (work tasks) 2.130.2#64
τ³-Banking · AA22.1#48
FAQ
How much does G9v3 39A5B cost?›
There is no per-unit API price: self-host only.
Is G9v3 39A5B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is G9v3 39A5B, and what is it best at?›
#133 of 334 in Chat & Knowledge, #109 of 140 in Coding, #64 of 175 in Agents & Tool Use. Strongest at: Knowledge.
Is G9v3 39A5B better than o3 Pro?›
On AA Intelligence Index 4.3.2, G9v3 39A5B scores 21.8 vs 21.9 — about the same.
What is the context window of G9v3 39A5B?›
131K tokens.
When was G9v3 39A5B released? Is there a newer version?›
Released 2026-08-20. It is the current version in its line.
Is G9v3 39A5B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run G9v3 39A5B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can G9v3 39A5B read images?›
No, it accepts text only.
What is G9v3 39A5B?›
G9v3 39A5B is an open-weights language model from AI9Stars, released Aug 2026.
What are the best alternatives to G9v3 39A5B?›
GPT-5.6 Luna (better), Qwen3.8 27B (open weights).